Dark Reading·4d agoDeception by Design: CISA's Guide to Tricking Cybercriminals#cisa#deception#honeypot
arXiv cs.CR·4d agoRouxii: Exploiting Honeypots with Deception-Aware AI Pentesters#honeypot#llm-agents#pentestingAI safety & security
arXiv cs.AI / cs.LG / cs.CL·8d agoA Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal#sandbagging#unlearning#deceptionAI safety & security
Hugging Face daily papers·9d agoA Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal#alignment#deception#evals
Cyber Security News·9d agoOpenAI Models Searched for Leaked API Keys and Uploaded Files Without Permission#agentic-ai#ai-safety#data-exfiltration 4 min1
Cyber Security News·9d agoCISA Wants Defenders to Plant Fake Credentials and Systems to Catch Hackers#cisa#deception#decoys 3 min
GBHackers·9d agoCISA Urges Organizations to Deploy Cyber Decoys to Detect Hackers Inside Networks#cisa#deception#decoys 3 min
SecurityWeek·10d agoCISA Releases Guidance on Deploying Cyber Decoys#cisa#critical-infrastructure#deception 2 min
CyberScoop·10d agoCISA promotes a fresh way to deter cyberattackers: Lie to them#cisa#critical-infrastructure#deception 3 min
arXiv cs.AI / cs.LG / cs.CL·12d agoCorrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection#ai-safety#chain-of-thought-monitoring#deceptionAI safety & security
The Decoder·15d agoDeep learning pioneer Bengio argues the training process itself makes AI dangerous#agentic-ai#ai-safety#alignment1
Help Net Security·17d agoProduct showcase: GitGuardian Honeytoken catches credential theft as it happens#aws#credentials#deception 7 min1
arXiv cs.CR·19d agoLLM-Based Penetration Testing in the Presence of Honeypots#deception#honeypots#llm-agentsResearch
Malwarebytes Labs·19d agoFlirty OnlyFans promoters on X may be using AI to appear human#chatbots#deception#generative-ai 7 min